Computing ordinary least squares regression

The OLSMultipleLinearRegression provides Ordinary Least Squares Regression to fit the linear model Y=X*b+u. Here, Y is an n-vector regress, and X is a [n,k] matrix, where k columns are called regressors, b is k-vector of regression parameters, and u is an n-vector of error terms or residuals.

How to do it...

1. Create a method that takes a two-dimensional double array and a one-dimensional double array:

           public void calculateOlsRegression(double[][] x, double[] y){ 
   

2. Create an OLS regression object and add the data points x and y:

           OLSMultipleLinearRegression regression = new 
             OLSMultipleLinearRegression(); 
           regression.newSampleData(y, x); 
   

3. Calculate various regression parameters and diagnostics using the following methods in the OLSMultipleLinearRegression class. The usage of these information depends on your task in hand. Finally, close the method:

           double[] beta = regression.estimateRegressionParameters...